如何将wstring转换为字符串?

问题是如何将wstring转换为字符串?

我还有一个例子:

#include <string>
#include <iostream>

int main()
{
    std::wstring ws = L"Hello";
    std::string s( ws.begin(), ws.end() );

  //std::cout <<"std::string =     "<<s<<std::endl;
    std::wcout<<"std::wstring =    "<<ws<<std::endl;
    std::cout <<"std::string =     "<<s<<std::endl;
}

带注释的输出为:

std::string =     Hello
std::wstring =    Hello
std::string =     Hello

但是without只是:

std::wstring =    Hello

这个例子中有什么问题吗?我可以像上面那样进行转换吗?

EDIT

新例子(考虑到一些答案)是

#include <string>
#include <iostream>
#include <sstream>
#include <locale>

int main()
{
    setlocale(LC_CTYPE, "");

    const std::wstring ws = L"Hello";
    const std::string s( ws.begin(), ws.end() );

    std::cout<<"std::string =     "<<s<<std::endl;
    std::wcout<<"std::wstring =    "<<ws<<std::endl;

    std::stringstream ss;
    ss << ws.c_str();
    std::cout<<"std::stringstream =     "<<ss.str()<<std::endl;
}

输出结果为:

std::string =     Hello
std::wstring =    Hello
std::stringstream =     0x860283c

因此，不能使用stringstream将wstring转换为string。

当前回答

下面是一个基于其他建议的解决方案:

#include <string>
#include <iostream>
#include <clocale>
#include <locale>
#include <vector>

int main() {
  std::setlocale(LC_ALL, "");
  const std::wstring ws = L"ħëłlö";
  const std::locale locale("");
  typedef std::codecvt<wchar_t, char, std::mbstate_t> converter_type;
  const converter_type& converter = std::use_facet<converter_type>(locale);
  std::vector<char> to(ws.length() * converter.max_length());
  std::mbstate_t state;
  const wchar_t* from_next;
  char* to_next;
  const converter_type::result result = converter.out(state, ws.data(), ws.data() + ws.length(), from_next, &to[0], &to[0] + to.size(), to_next);
  if (result == converter_type::ok or result == converter_type::noconv) {
    const std::string s(&to[0], to_next);
    std::cout <<"std::string =     "<<s<<std::endl;
  }
}

这通常适用于Linux，但会在Windows上产生问题。

2011-01-26 14:06:15

其他回答

// Embarcadero C++ Builder 

// convertion string to wstring
string str1 = "hello";
String str2 = str1;         // typedef UnicodeString String;   -> str2 contains now u"hello";

// convertion wstring to string
String str2 = u"hello";
string str1 = UTF8string(str2).c_str();   // -> str1 contains now "hello"

2014-11-11 11:27:57

下面是一个基于其他建议的解决方案:

#include <string>
#include <iostream>
#include <clocale>
#include <locale>
#include <vector>

int main() {
  std::setlocale(LC_ALL, "");
  const std::wstring ws = L"ħëłlö";
  const std::locale locale("");
  typedef std::codecvt<wchar_t, char, std::mbstate_t> converter_type;
  const converter_type& converter = std::use_facet<converter_type>(locale);
  std::vector<char> to(ws.length() * converter.max_length());
  std::mbstate_t state;
  const wchar_t* from_next;
  char* to_next;
  const converter_type::result result = converter.out(state, ws.data(), ws.data() + ws.length(), from_next, &to[0], &to[0] + to.size(), to_next);
  if (result == converter_type::ok or result == converter_type::noconv) {
    const std::string s(&to[0], to_next);
    std::cout <<"std::string =     "<<s<<std::endl;
  }
}

这通常适用于Linux，但会在Windows上产生问题。

2011-01-26 14:06:15

在我的情况下，我必须使用多字节字符(MBCS)，我想使用std::string和std::wstring。不能使用c++11。所以我使用mbstowcs和wcstombs。

我与使用new, delete[]做相同的函数，但它比这更慢。

这可以帮助如何:在各种字符串类型之间转换

EDIT

然而，在转换为wstring和源字符串是没有字母和多字节字符串的情况下，它是不工作的。所以我把wcstombs改成WideCharToMultiByte。

#include <string>

std::wstring get_wstr_from_sz(const char* psz)
{
    //I think it's enough to my case
    wchar_t buf[0x400];
    wchar_t *pbuf = buf;
    size_t len = strlen(psz) + 1;

    if (len >= sizeof(buf) / sizeof(wchar_t))
    {
        pbuf = L"error";
    }
    else
    {
        size_t converted;
        mbstowcs_s(&converted, buf, psz, _TRUNCATE);
    }

    return std::wstring(pbuf);
}

std::string get_string_from_wsz(const wchar_t* pwsz)
{
    char buf[0x400];
    char *pbuf = buf;
    size_t len = wcslen(pwsz)*2 + 1;

    if (len >= sizeof(buf))
    {
        pbuf = "error";
    }
    else
    {
        size_t converted;
        wcstombs_s(&converted, buf, pwsz, _TRUNCATE);
    }

    return std::string(pbuf);
}

编辑使用“MultiByteToWideChar”而不是“wcstombs”

#include <Windows.h>
#include <boost/shared_ptr.hpp>
#include "string_util.h"

std::wstring get_wstring_from_sz(const char* psz)
{
    int res;
    wchar_t buf[0x400];
    wchar_t *pbuf = buf;
    boost::shared_ptr<wchar_t[]> shared_pbuf;

    res = MultiByteToWideChar(CP_ACP, 0, psz, -1, buf, sizeof(buf)/sizeof(wchar_t));

    if (0 == res && GetLastError() == ERROR_INSUFFICIENT_BUFFER)
    {
        res = MultiByteToWideChar(CP_ACP, 0, psz, -1, NULL, 0);

        shared_pbuf = boost::shared_ptr<wchar_t[]>(new wchar_t[res]);

        pbuf = shared_pbuf.get();

        res = MultiByteToWideChar(CP_ACP, 0, psz, -1, pbuf, res);
    }
    else if (0 == res)
    {
        pbuf = L"error";
    }

    return std::wstring(pbuf);
}

std::string get_string_from_wcs(const wchar_t* pcs)
{
    int res;
    char buf[0x400];
    char* pbuf = buf;
    boost::shared_ptr<char[]> shared_pbuf;

    res = WideCharToMultiByte(CP_ACP, 0, pcs, -1, buf, sizeof(buf), NULL, NULL);

    if (0 == res && GetLastError() == ERROR_INSUFFICIENT_BUFFER)
    {
        res = WideCharToMultiByte(CP_ACP, 0, pcs, -1, NULL, 0, NULL, NULL);

        shared_pbuf = boost::shared_ptr<char[]>(new char[res]);

        pbuf = shared_pbuf.get();

        res = WideCharToMultiByte(CP_ACP, 0, pcs, -1, pbuf, res, NULL, NULL);
    }
    else if (0 == res)
    {
        pbuf = "error";
    }

    return std::string(pbuf);
}

2014-03-31 15:54:27

这个解决方案的灵感来自dk123的解决方案，但是使用了一个依赖于地区的codecvt facet。结果是区域编码的字符串而不是UTF-8(如果它没有设置为区域设置):

std::string w2s(const std::wstring &var)
{
   static std::locale loc("");
   auto &facet = std::use_facet<std::codecvt<wchar_t, char, std::mbstate_t>>(loc);
   return std::wstring_convert<std::remove_reference<decltype(facet)>::type, wchar_t>(&facet).to_bytes(var);
}

std::wstring s2w(const std::string &var)
{
   static std::locale loc("");
   auto &facet = std::use_facet<std::codecvt<wchar_t, char, std::mbstate_t>>(loc);
   return std::wstring_convert<std::remove_reference<decltype(facet)>::type, wchar_t>(&facet).from_bytes(var);
}

我一直在找，但我找不到。最后，我发现我可以从std::locale使用std::use_facet()函数与正确的typename获得正确的facet。希望这能有所帮助。

2016-04-27 14:57:25

代码有两个问题:

The conversion in const std::string s( ws.begin(), ws.end() ); is not required to correctly map the wide characters to their narrow counterpart. Most likely, each wide character will just be typecast to char. The resolution to this problem is already given in the answer by kem and involves the narrow function of the locale's ctype facet. You are writing output to both std::cout and std::wcout in the same program. Both cout and wcout are associated with the same stream (stdout) and the results of using the same stream both as a byte-oriented stream (as cout does) and a wide-oriented stream (as wcout does) are not defined. The best option is to avoid mixing narrow and wide output to the same (underlying) stream. For stdout/cout/wcout, you can try switching the orientation of stdout when switching between wide and narrow output (or vice versa): #include <iostream> #include <stdio.h> #include <wchar.h> int main() { std::cout << "narrow" << std::endl; fwide(stdout, 1); // switch to wide std::wcout << L"wide" << std::endl; fwide(stdout, -1); // switch to narrow std::cout << "narrow" << std::endl; fwide(stdout, 1); // switch to wide std::wcout << L"wide" << std::endl; }

2011-01-26 13:33:26

如何将wstring转换为字符串?

推荐文章

最新文章

标签